Whitespace.
See who already built your idea — and the space they left open.

CLUSTER DESKTOP-AGENTS-LOCAL · 32 ENTRIES · EARLIEST ENTRY 2026-08-25

Local AI model workbenches

This cluster comprises desktop applications for running, testing, and tuning local AI models, often with agent execution and user-selected model providers. The dated history is too thin to read a shape from, with only four dated entries before the index started, so the cluster predates the index or its members are largely undated. On traction, dsh-desktop leads with 6,823 stars, followed by vibe-holding at 201 and laobos-agent-studio at 12.

Entry timeline

ENTRY TIMELINE

NOV 2025: 1APR 2026: 1AUG 2026: 6SEP 2026: 16OCT 2026: 8
NOV 2025OCT 2026

Each bar is the month a member carries, which is a creation date where the source published one and a crawl date otherwise. Nothing in the index was found before 11 August 2026, and coverage broadened sharply on 14–15 August, so a bar from then on reports how much we found that month, not how much was built; an earlier bar reports how far back a member's own source dated it — not how long we have been watching.

Members by activity

Activity signals, not revenue.

Build origin · 12 unlabelled

Operator · 7 hobby · 5 unlabelled

Two labels per entry, never collapsed into one: how it was built, and who stands behind it. Counted over the 12 listed below. Unlabelled means nothing has decided yet — not that the answer is small.

  1. 21hangar0★today—hobbyDesktop utility that manages local AI model servers on a Mac, providing a single web page, command-line interface, and OpenAI-compatible endpoint to start, stop, and monitor them.
  2. 22.github0★10 days—Cross-platform desktop app that downloads, runs, and manages local AI models through a graphical interface with an agent terminal.
  3. 23Jobs-Express0★2 days—Local app that automates job applications by running AI agents in the user's browser, with data stored on the user's machine.
  4. 24runtimedeck0★10 daysliveDesktop application for running local AI models, launching inference and benchmarks, chatting with a local server, and preserving reproducible experiment evidence.
  5. 25born-studio0★26 days—hobbyLocal artificial-life sandbox that runs simulated agents learning from experience and lets users transplant learned weights between them.
  6. 26local-model-bench0★6 days—hobbyDesktop app that benchmarks locally installed AI models by measuring response speed, answer correctness, and GPU temperature.
  7. 27Monolith7★1 mo—hobbyDesktop AI client that connects to multiple providers with personal API keys, runs local models, and manages cooperating AI agents.
  8. 28NInfer-Manager1★1 mo—hobbyDesktop tray application that manages local AI inference models and provides a graphical interface for monitoring and controlling the inference server.
  9. 29DeepSeek-Harness-Desktop2★1 mo—Desktop application that bundles an embedded AI server with a user interface for easy running local language models.
  10. 30image-pick0★1 mo—hobbyLocal-first desktop app that lets humans review image batches, compare references, mark selections, and send structured feedback to AI agents.
  11. 31llm-hardware-architect0★5 moliveAn online tool that checks whether a GPU can run local AI models and estimates performance.
  12. 32tora0★11 mostale—hobbyDesktop application that manages and runs local AI models, including language models and image generators, without relying on cloud services.

Ranked by traction, highest first, and paged 20 at a time — this is a window on the cluster, never the whole of it. Ties are broken by a stable id so a product cannot appear on two pages or fall between them. Browse every cluster.